mirror of
https://github.com/hwchase17/langchain.git
synced 2025-04-27 11:41:51 +00:00
docs: Astra DB, replace leftover links to "community" legacy package + modernize doc loader signature (#30969)
This PR brings some much-needed updates to some of the Astra DB shorter example notebooks, - ensuring imports are from the partner package instead of the (deprecated) community legacy package - improving the wording in a few related places - updating the constructor signature introduced with the latest partner package's AstraDBLoader - marking the community package counterpart of the LLM caches as deprecated in the summary table at the end of the page.
This commit is contained in:
Stefano Lottini
GitHub
parent
a60fd06784
commit
a82d987f09
@ -34,33 +34,46 @@
|
||||
"id": "juAmbgoWD17u"
|
||||
},
|
||||
"source": [
|
||||
"The AstraDB Document Loader returns a list of Langchain Documents from an AstraDB database.\n",
|
||||
"The Astra DB Document Loader returns a list of Langchain `Document` objects read from an Astra DB collection.\n",
|
||||
"\n",
|
||||
"The Loader takes the following parameters:\n",
|
||||
"The loader takes the following parameters:\n",
|
||||
"\n",
|
||||
"* `api_endpoint`: AstraDB API endpoint. Looks like `https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com`\n",
|
||||
"* `token`: AstraDB token. Looks like `AstraCS:6gBhNmsk135....`\n",
|
||||
"* `api_endpoint`: Astra DB API endpoint. Looks like `https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com`\n",
|
||||
"* `token`: Astra DB token. Looks like `AstraCS:aBcD0123...`\n",
|
||||
"* `collection_name` : AstraDB collection name\n",
|
||||
"* `namespace`: (Optional) AstraDB namespace\n",
|
||||
"* `namespace`: (Optional) AstraDB namespace (called _keyspace_ in Astra DB)\n",
|
||||
"* `filter_criteria`: (Optional) Filter used in the find query\n",
|
||||
"* `projection`: (Optional) Projection used in the find query\n",
|
||||
"* `find_options`: (Optional) Options used in the find query\n",
|
||||
"* `nb_prefetched`: (Optional) Number of documents pre-fetched by the loader\n",
|
||||
"* `limit`: (Optional) Maximum number of documents to retrieve\n",
|
||||
"* `extraction_function`: (Optional) A function to convert the AstraDB document to the LangChain `page_content` string. Defaults to `json.dumps`\n",
|
||||
"\n",
|
||||
"The following metadata is set to the LangChain Documents metadata output:\n",
|
||||
"The loader sets the following metadata for the documents it reads:\n",
|
||||
"\n",
|
||||
"```python\n",
|
||||
"{\n",
|
||||
" metadata : {\n",
|
||||
"metadata={\n",
|
||||
" \"namespace\": \"...\", \n",
|
||||
" \"api_endpoint\": \"...\", \n",
|
||||
" \"collection\": \"...\"\n",
|
||||
" }\n",
|
||||
"}\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setup"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install \"langchain-astradb>=0.6,<0.7\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
@ -71,24 +84,43 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_community.document_loaders import AstraDBLoader"
|
||||
"from langchain_astradb import AstraDBLoader"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"[**API Reference:** `AstraDBLoader`](https://python.langchain.com/api_reference/astradb/document_loaders/langchain_astradb.document_loaders.AstraDBLoader.html#langchain_astradb.document_loaders.AstraDBLoader)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 3,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-01-08T12:41:22.643335Z",
|
||||
"start_time": "2024-01-08T12:40:57.759116Z"
|
||||
},
|
||||
"collapsed": false
|
||||
"collapsed": false,
|
||||
"jupyter": {
|
||||
"outputs_hidden": false
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdin",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"ASTRA_DB_API_ENDPOINT = https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com\n",
|
||||
"ASTRA_DB_APPLICATION_TOKEN = ········\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from getpass import getpass\n",
|
||||
"\n",
|
||||
@ -98,7 +130,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": 4,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-01-08T12:42:25.395162Z",
|
||||
@ -112,19 +144,22 @@
|
||||
" token=ASTRA_DB_APPLICATION_TOKEN,\n",
|
||||
" collection_name=\"movie_reviews\",\n",
|
||||
" projection={\"title\": 1, \"reviewtext\": 1},\n",
|
||||
" find_options={\"limit\": 10},\n",
|
||||
" limit=10,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": 5,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-01-08T12:42:30.236489Z",
|
||||
"start_time": "2024-01-08T12:42:29.612133Z"
|
||||
},
|
||||
"collapsed": false
|
||||
"collapsed": false,
|
||||
"jupyter": {
|
||||
"outputs_hidden": false
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -133,7 +168,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"execution_count": 6,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-01-08T12:42:31.369394Z",
|
||||
@ -144,10 +179,10 @@
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"Document(page_content='{\"_id\": \"659bdffa16cbc4586b11a423\", \"title\": \"Dangerous Men\", \"reviewtext\": \"\\\\\"Dangerous Men,\\\\\" the picture\\'s production notes inform, took 26 years to reach the big screen. After having seen it, I wonder: What was the rush?\"}', metadata={'namespace': 'default_keyspace', 'api_endpoint': 'https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com', 'collection': 'movie_reviews'})"
|
||||
"Document(metadata={'namespace': 'default_keyspace', 'api_endpoint': 'https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com', 'collection': 'movie_reviews'}, page_content='{\"_id\": \"659bdffa16cbc4586b11a423\", \"title\": \"Dangerous Men\", \"reviewtext\": \"\\\\\"Dangerous Men,\\\\\" the picture\\'s production notes inform, took 26 years to reach the big screen. After having seen it, I wonder: What was the rush?\"}')"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@ -179,7 +214,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.18"
|
||||
"version": "3.12.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@ -3112,8 +3112,8 @@
|
||||
"|------------|---------|\n",
|
||||
"| langchain_astradb.cache | [AstraDBCache](https://python.langchain.com/api_reference/astradb/cache/langchain_astradb.cache.AstraDBCache.html) |\n",
|
||||
"| langchain_astradb.cache | [AstraDBSemanticCache](https://python.langchain.com/api_reference/astradb/cache/langchain_astradb.cache.AstraDBSemanticCache.html) |\n",
|
||||
"| langchain_community.cache | [AstraDBCache](https://python.langchain.com/api_reference/community/cache/langchain_community.cache.AstraDBCache.html) |\n",
|
||||
"| langchain_community.cache | [AstraDBSemanticCache](https://python.langchain.com/api_reference/community/cache/langchain_community.cache.AstraDBSemanticCache.html) |\n",
|
||||
"| langchain_community.cache | [AstraDBCache](https://python.langchain.com/api_reference/community/cache/langchain_community.cache.AstraDBCache.html) (deprecated since `langchain-community==0.0.28`) |\n",
|
||||
"| langchain_community.cache | [AstraDBSemanticCache](https://python.langchain.com/api_reference/community/cache/langchain_community.cache.AstraDBSemanticCache.html) (deprecated since `langchain-community==0.0.28`) |\n",
|
||||
"| langchain_community.cache | [AzureCosmosDBSemanticCache](https://python.langchain.com/api_reference/community/cache/langchain_community.cache.AzureCosmosDBSemanticCache.html) |\n",
|
||||
"| langchain_community.cache | [CassandraCache](https://python.langchain.com/api_reference/community/cache/langchain_community.cache.CassandraCache.html) |\n",
|
||||
"| langchain_community.cache | [CassandraSemanticCache](https://python.langchain.com/api_reference/community/cache/langchain_community.cache.CassandraSemanticCache.html) |\n",
|
||||
|
||||
@ -17,22 +17,22 @@
|
||||
"id": "f507f58b-bf22-4a48-8daf-68d869bcd1ba",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setting up\n",
|
||||
"## Setup\n",
|
||||
"\n",
|
||||
"To run this notebook you need a running Astra DB. Get the connection secrets on your Astra dashboard:\n",
|
||||
"\n",
|
||||
"- the API Endpoint looks like `https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com`;\n",
|
||||
"- the Token looks like `AstraCS:6gBhNmsk135...`."
|
||||
"- the Database Token looks like `AstraCS:aBcD0123...`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 1,
|
||||
"id": "d7092199",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install --upgrade --quiet \"astrapy>=0.7.1 langchain-community\" "
|
||||
"!pip install \"langchain-astradb>=0.6,<0.7\""
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -45,12 +45,12 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"execution_count": 2,
|
||||
"id": "163d97f0",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"name": "stdin",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"ASTRA_DB_API_ENDPOINT = https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com\n",
|
||||
@ -65,14 +65,6 @@
|
||||
"ASTRA_DB_APPLICATION_TOKEN = getpass.getpass(\"ASTRA_DB_APPLICATION_TOKEN = \")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "55860b2d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Depending on whether local or cloud-based Astra DB, create the corresponding database connection \"Session\" object."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "36c163e8",
|
||||
@ -83,12 +75,12 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": 3,
|
||||
"id": "d15e3302",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_community.chat_message_histories import AstraDBChatMessageHistory\n",
|
||||
"from langchain_astradb import AstraDBChatMessageHistory\n",
|
||||
"\n",
|
||||
"message_history = AstraDBChatMessageHistory(\n",
|
||||
" session_id=\"test-session\",\n",
|
||||
@ -98,22 +90,31 @@
|
||||
"\n",
|
||||
"message_history.add_user_message(\"hi!\")\n",
|
||||
"\n",
|
||||
"message_history.add_ai_message(\"whats up?\")"
|
||||
"message_history.add_ai_message(\"hello, how are you?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "53acb4a8-d536-4a58-9fee-7d70033d9c81",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"[**API Reference:** `AstraDBChatMessageHistory`](https://python.langchain.com/api_reference/astradb/chat_message_histories/langchain_astradb.chat_message_histories.AstraDBChatMessageHistory.html#langchain_astradb.chat_message_histories.AstraDBChatMessageHistory)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 4,
|
||||
"id": "64fc465e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[HumanMessage(content='hi!'), AIMessage(content='whats up?')]"
|
||||
"[HumanMessage(content='hi!', additional_kwargs={}, response_metadata={}),\n",
|
||||
" AIMessage(content='hello, how are you?', additional_kwargs={}, response_metadata={})]"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@ -139,7 +140,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.12"
|
||||
"version": "3.12.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@ -4,7 +4,7 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Astra DB (Cassandra)\n",
|
||||
"# Astra DB\n",
|
||||
"\n",
|
||||
">[DataStax Astra DB](https://docs.datastax.com/en/astra/home/astra.html) is a serverless vector-capable database built on `Cassandra` and made conveniently available through an easy-to-use JSON API.\n",
|
||||
"\n",
|
||||
@ -16,32 +16,46 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Creating an Astra DB vector store\n",
|
||||
"First we'll want to create an Astra DB VectorStore and seed it with some data. We've created a small demo set of documents that contain summaries of movies.\n",
|
||||
"First, create an Astra DB vector store and seed it with some data.\n",
|
||||
"\n",
|
||||
"NOTE: The self-query retriever requires you to have `lark` installed (`pip install lark`). We also need the `astrapy` package."
|
||||
"We've created a small demo set of documents containing movie summaries.\n",
|
||||
"\n",
|
||||
"NOTE: The self-query retriever requires the `lark` package installed (`pip install lark`)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"scrolled": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install --upgrade --quiet lark astrapy langchain-openai"
|
||||
"!pip install \"langchain-astradb>=0.6,<0.7\" \\\n",
|
||||
" \"langchain_openai>=0.3,<0.4\" \\\n",
|
||||
" \"lark>=1.2,<2.0\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We want to use `OpenAIEmbeddings` so we have to get the OpenAI API Key."
|
||||
"In this example, you'll use the `OpenAIEmbeddings`. Please enter an OpenAI API Key."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdin",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"OpenAI API Key: ········\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"from getpass import getpass\n",
|
||||
@ -69,14 +83,23 @@
|
||||
"Create the Astra DB VectorStore:\n",
|
||||
"\n",
|
||||
"- the API Endpoint looks like `https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com`\n",
|
||||
"- the Token looks like `AstraCS:6gBhNmsk135....`"
|
||||
"- the Token looks like `AstraCS:aBcD0123...`"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdin",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"ASTRA_DB_API_ENDPOINT = https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com\n",
|
||||
"ASTRA_DB_APPLICATION_TOKEN = ········\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"ASTRA_DB_API_ENDPOINT = input(\"ASTRA_DB_API_ENDPOINT = \")\n",
|
||||
"ASTRA_DB_APPLICATION_TOKEN = getpass(\"ASTRA_DB_APPLICATION_TOKEN = \")"
|
||||
@ -84,11 +107,11 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_community.vectorstores import AstraDB\n",
|
||||
"from langchain_astradb import AstraDBVectorStore\n",
|
||||
"from langchain_core.documents import Document\n",
|
||||
"\n",
|
||||
"docs = [\n",
|
||||
@ -101,11 +124,13 @@
|
||||
" metadata={\"year\": 2010, \"director\": \"Christopher Nolan\", \"rating\": 8.2},\n",
|
||||
" ),\n",
|
||||
" Document(\n",
|
||||
" page_content=\"A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea\",\n",
|
||||
" page_content=\"A psychologist / detective gets lost in a series of dreams within dreams \"\n",
|
||||
" \"within dreams and Inception reused the idea\",\n",
|
||||
" metadata={\"year\": 2006, \"director\": \"Satoshi Kon\", \"rating\": 8.6},\n",
|
||||
" ),\n",
|
||||
" Document(\n",
|
||||
" page_content=\"A bunch of normal-sized women are supremely wholesome and some men pine after them\",\n",
|
||||
" page_content=\"A bunch of normal-sized women are supremely wholesome and some men \"\n",
|
||||
" \"pine after them\",\n",
|
||||
" metadata={\"year\": 2019, \"director\": \"Greta Gerwig\", \"rating\": 8.3},\n",
|
||||
" ),\n",
|
||||
" Document(\n",
|
||||
@ -123,7 +148,7 @@
|
||||
" ),\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"vectorstore = AstraDB.from_documents(\n",
|
||||
"vectorstore = AstraDBVectorStore.from_documents(\n",
|
||||
" docs,\n",
|
||||
" embeddings,\n",
|
||||
" collection_name=\"astra_self_query_demo\",\n",
|
||||
@ -136,13 +161,16 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Creating our self-querying retriever\n",
|
||||
"Now we can instantiate our retriever. To do this we'll need to provide some information upfront about the metadata fields that our documents support and a short description of the document contents."
|
||||
"## Creating a self-querying retriever\n",
|
||||
"\n",
|
||||
"Now you can instantiate the retriever.\n",
|
||||
"\n",
|
||||
"To do this, you need to provide some information upfront about the metadata fields that the documents support, along with a short description of the documents' contents."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -174,7 +202,11 @@
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"\n",
|
||||
"retriever = SelfQueryRetriever.from_llm(\n",
|
||||
" llm, vectorstore, document_content_description, metadata_field_info, verbose=True\n",
|
||||
" llm,\n",
|
||||
" vectorstore,\n",
|
||||
" document_content_description,\n",
|
||||
" metadata_field_info,\n",
|
||||
" verbose=True,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
@ -183,14 +215,29 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Testing it out\n",
|
||||
"And now we can try actually using our retriever!"
|
||||
"\n",
|
||||
"Now you can try actually using our retriever:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(id='d7b9ec1edafa467caab524455e8c1f5d', metadata={'year': 1993, 'rating': 7.7, 'genre': 'science fiction'}, page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose'),\n",
|
||||
" Document(id='8ad04ef2a73d4f74897a51e49be1a8d2', metadata={'year': 1995, 'genre': 'animated'}, page_content='Toys come alive and have a blast doing so'),\n",
|
||||
" Document(id='5b07e600d3494506952b60e0a45a0546', metadata={'year': 1979, 'director': 'Andrei Tarkovsky', 'genre': 'science fiction', 'rating': 9.9}, page_content='Three men walk into the Zone, three men walk out of the Zone'),\n",
|
||||
" Document(id='a0cef19e27c341929098ac4793602829', metadata={'year': 2006, 'director': 'Satoshi Kon', 'rating': 8.6}, page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea')]"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# This example only specifies a relevant query\n",
|
||||
"retriever.invoke(\"What are some movies about dinosaurs?\")"
|
||||
@ -198,9 +245,21 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(id='5b07e600d3494506952b60e0a45a0546', metadata={'year': 1979, 'director': 'Andrei Tarkovsky', 'genre': 'science fiction', 'rating': 9.9}, page_content='Three men walk into the Zone, three men walk out of the Zone'),\n",
|
||||
" Document(id='a0cef19e27c341929098ac4793602829', metadata={'year': 2006, 'director': 'Satoshi Kon', 'rating': 8.6}, page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea')]"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# This example specifies a filter\n",
|
||||
"retriever.invoke(\"I want to watch a movie rated higher than 8.5\")"
|
||||
@ -208,9 +267,20 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(id='0539843fd203484c9be486c2a0e2454c', metadata={'year': 2019, 'director': 'Greta Gerwig', 'rating': 8.3}, page_content='A bunch of normal-sized women are supremely wholesome and some men pine after them')]"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# This example only specifies a query and a filter\n",
|
||||
"retriever.invoke(\"Has Greta Gerwig directed any movies about women\")"
|
||||
@ -218,9 +288,21 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(id='a0cef19e27c341929098ac4793602829', metadata={'year': 2006, 'director': 'Satoshi Kon', 'rating': 8.6}, page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea'),\n",
|
||||
" Document(id='5b07e600d3494506952b60e0a45a0546', metadata={'year': 1979, 'director': 'Andrei Tarkovsky', 'genre': 'science fiction', 'rating': 9.9}, page_content='Three men walk into the Zone, three men walk out of the Zone')]"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# This example specifies a composite filter\n",
|
||||
"retriever.invoke(\"What's a highly rated (above 8.5), science fiction movie ?\")"
|
||||
@ -228,9 +310,20 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(id='8ad04ef2a73d4f74897a51e49be1a8d2', metadata={'year': 1995, 'genre': 'animated'}, page_content='Toys come alive and have a blast doing so')]"
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# This example specifies a query and composite filter\n",
|
||||
"retriever.invoke(\n",
|
||||
@ -242,20 +335,20 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Filter k\n",
|
||||
"## Set a limit ('k')\n",
|
||||
"\n",
|
||||
"We can also use the self query retriever to specify `k`: the number of documents to fetch.\n",
|
||||
"you can also use the self-query retriever to specify `k`, the number of documents to fetch.\n",
|
||||
"\n",
|
||||
"We can do this by passing `enable_limit=True` to the constructor."
|
||||
"You achieve this by passing `enable_limit=True` to the constructor."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"retriever = SelfQueryRetriever.from_llm(\n",
|
||||
"retriever_k = SelfQueryRetriever.from_llm(\n",
|
||||
" llm,\n",
|
||||
" vectorstore,\n",
|
||||
" document_content_description,\n",
|
||||
@ -267,12 +360,24 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(id='d7b9ec1edafa467caab524455e8c1f5d', metadata={'year': 1993, 'rating': 7.7, 'genre': 'science fiction'}, page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose'),\n",
|
||||
" Document(id='8ad04ef2a73d4f74897a51e49be1a8d2', metadata={'year': 1995, 'genre': 'animated'}, page_content='Toys come alive and have a blast doing so')]"
|
||||
]
|
||||
},
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# This example only specifies a relevant query\n",
|
||||
"retriever.invoke(\"What are two movies about dinosaurs?\")"
|
||||
"retriever_k.invoke(\"What are two movies about dinosaurs?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -293,7 +398,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 12,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"jupyter": {
|
||||
@ -322,7 +427,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.12"
|
||||
"version": "3.12.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
Loading…
Reference in New Issue
Block a user